HHT-based classification of composite power quality events

Abstract

Purpose – An electrical power system is expected to deliver undistorted sinusoidal, rated voltage and current continuously to the end-users. The problem of power quality (PQ) occurs when there is (are) deviation(s) in voltage and/or current which cause(s) failure or mal-operation of the customer's equipments. Various methods are suggested to detect and classify single PQ event in a power system, the performance of such methods to classify composite PQ events is limited. The purpose of this paper is the classification of composite PQ events in emerging power systems. Design/methodology/approach – This paper proposes an effective method to classify composite PQ events using Hilbert Huang transform (HHT). The performance of probabilistic neural network (PNN) classifier and support vector machine (SVM) classifier to efficiently classify composite PQ events is compared. Findings – The features extracted from HHT are simple yet effective. SVMs and PNN classifiers are used for PQ classification. It is found that PNN classifier outperforms SVM with the classification accuracy of 100 percent. Originality/value – Different PQ signals used for analysis are generated by simulating a practical distribution system of an Indian academic institution.